Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks

doi:10.3390/electronics10172091

	Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks
	Cao, Qinghua 2; Yu, Lisu 2,3; Wang, Zhen 2; Zhan, Shanjun 2; Quan, Hao 2; Yu, Yan 1; Khan, Zahid 4; Koubaa, Anis 4
刊名	ELECTRONICS
	2021-09-01
卷号	10 期号:17 页码:16
关键词	information collection internet of things deep neural network SDN object detection
DOI	10.3390/electronics10172091
英文摘要	The wild animal information collection based on the wireless sensor network (WSN) has an enormous number of applications, as demonstrated in the literature. Yet, it has many problems, such as low information density and high energy consumption ratio. The traditional Internet of Things (IoT) system has characteristics of limited resources and task specificity. Therefore, we introduce an improved deep neural network (DNN) structure to solve task specificity. In addition, we determine a programmability idea of software-defined network (SDN) to solve the problems of high energy consumption ratio and low information density brought about by low autonomy of equipment. By introducing some advanced network structures, such as attention mechanism, residuals, depthwise (DW) convolution, pointwise (PW) convolution, spatial pyramid pooling (SPP), and feature pyramid networks (FPN), a lightweight object detection network with a fast response is designed. Meanwhile, the concept of control plane and data plane in SDN is introduced, and nodes are divided into different types to facilitate intelligent wake-up, thereby realizing high-precision detection and high information density of the detection system. The results show that the proposed scheme can improve the detection response speed and reduce the model parameters while ensuring detection accuracy in the software-defined IoT networks.
资助项目	National Science Foundation of China (NSFC)[62161024] ; State Key Laboratory of Computer Architecture (ICT, CAS) Open Project[CARCHB202019] ; China Postdoctoral Science Foundation[2021TQ0136] ; Training Program of Innovation and Entrepreneurship for Undergraduates in Nanchang University[2020CX234] ; Training Program of Innovation and Entrepreneurship for Undergraduates in Nanchang University[2020CX236] ; Student Research Training Program (SRTP) in Nanchang University[5258] ; Student Research Training Program (SRTP) in Nanchang University[5259] ; Prince Sultan University, Saudi Arabia
WOS研究方向	Computer Science ; Engineering ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000695553200001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17191]
专题	中国科学院计算技术研究所
通讯作者	Yu, Lisu; Wang, Zhen
作者单位	1.Jingdezhen Ceram Univ, Sch Informat Engn, Jingdezhen 333403, Peoples R China 2.Nanchang Univ, Sch Informat Engn, Nanchang 330031, Jiangxi, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 4.Prince Sultan Univ, Coll Comp & Informat Sci, Riyadh 11586, Saudi Arabia
推荐引用方式 GB/T 7714	Cao, Qinghua,Yu, Lisu,Wang, Zhen,et al. Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks[J]. ELECTRONICS,2021,10(17):16.
APA	Cao, Qinghua.,Yu, Lisu.,Wang, Zhen.,Zhan, Shanjun.,Quan, Hao.,...&Koubaa, Anis.(2021).Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks.ELECTRONICS,10(17),16.
MLA	Cao, Qinghua,et al."Wild Animal Information Collection Based on Depthwise Separable Convolution in Software Defined IoT Networks".ELECTRONICS 10.17(2021):16.